← All changes | jetpack_vendor/automattic/jetpack-waf/src/class-waf-transforms.php +47 -5 13.2.4 → 16.3 View file →

		@@ -349,13 +349,55 @@
349	349	return trim( $value, self::TRIM_CHARS );
350	350	}
351	351
352	352	/**
353		- * Convert utf-8 characters to unicode characters
	353	+ * Convert UTF-8 characters to Unicode characters.
354	354	*
355		- * @param string $value value to be encoded.
356		- * @return string
	355	+ * This function iterates through each character of the input string, checks the ASCII value,
	356	+ * and converts it to its corresponding Unicode representation. It handles characters that are
	357	+ * represented with 1 to 4 bytes in UTF-8.
	358	+ *
	359	+ * @param string $str The string value to be encoded from UTF-8 to Unicode.
	360	+ * @return string The converted string with Unicode representation.
357	361	*/
358		- public function utf8_to_unicode( $value ) {
359		- return preg_replace( '/\\\u(?=[a-f0-9]{4})/', '%u', substr( json_encode( $value ), 1, -1 ) );
	362	+ public function utf8_to_unicode( $str ) {
	363	+ $unicodeStr = '';
	364	+ $strLen = strlen( $str );
	365	+ $i = 0;
	366	+
	367	+ // Iterate through each character of the input string.
	368	+ while ( $i < $strLen ) {
	369	+ // Get the ASCII value of the current character.
	370	+ $value = ord( $str[ $i ] );
	371	+
	372	+ if ( $value < 128 ) {
	373	+ // If the character is in the ASCII range (0-127), directly add it to the Unicode string.
	374	+ $unicodeStr .= chr( $value );
	375	+ ++$i;
	376	+ } else {
	377	+ // For characters outside the ASCII range, determine the number of bytes in the UTF-8 representation.
	378	+ $unicodeValue = '';
	379	+ if ( $value >= 192 && $value <= 223 ) {
	380	+ // For characters represented with 2 bytes in UTF-8.
	381	+ $unicodeValue = ( ord( $str[ $i ] ) & 0x1F ) << 6 | ( ord( $str[ $i + 1 ] ) & 0x3F );
	382	+ $i += 2;
	383	+ } elseif ( $value >= 224 && $value <= 239 ) {
	384	+ // For characters represented with 3 bytes in UTF-8.
	385	+ $unicodeValue = ( ord( $str[ $i ] ) & 0x0F ) << 12 | ( ord( $str[ $i + 1 ] ) & 0x3F ) << 6 | ( ord( $str[ $i + 2 ] ) & 0x3F );
	386	+ $i += 3;
	387	+ } elseif ( $value >= 240 && $value <= 247 ) {
	388	+ // For characters represented with 4 bytes in UTF-8.
	389	+ $unicodeValue = ( ord( $str[ $i ] ) & 0x07 ) << 18 | ( ord( $str[ $i + 1 ] ) & 0x3F ) << 12 | ( ord( $str[ $i + 2 ] ) & 0x3F ) << 6 | ( ord( $str[ $i + 3 ] ) & 0x3F );
	390	+ $i += 4;
	391	+ } else {
	392	+ // If the sequence does not match any known UTF-8 pattern, skip to the next character.
	393	+ ++$i;
	394	+ continue;
	395	+ }
	396	+ // Convert the Unicode value to a formatted string and append it to the Unicode string.
	397	+ $unicodeStr .= sprintf( '%%u%04X', $unicodeValue );
	398	+ }
	399	+ }
	400	+
	401	+ return strtolower( $unicodeStr );
360	402	}
361	403	}